Read usedby from your code or your AI assistant

Connect an AI assistant to the MCP server, or call the JSON API at /api/v1. Add .md to most page URLs for Markdown, in English, and /llms.txt lists the main pages. No key, no account.

Connect the MCP server Open llms.txt

# Connect Claude Code to the usedby MCP server
claude mcp add --transport http usedby https://www.usedby.ai/mcp

# Any MCP client: Streamable HTTP, no key
https://www.usedby.ai/mcp

# Who uses Harvey, strongest proof first
curl -L "https://www.usedby.ai/api/v1/tools/harvey/customers?limit=3"

# Every endpoint, and the OpenAPI description
curl -L https://www.usedby.ai/api/v1
curl -L https://www.usedby.ai/api/v1/openapi.json

# Markdown version of https://www.usedby.ai/tools/harvey
curl -L https://www.usedby.ai/tools/harvey.md

# Search tools and companies by name
curl -L "https://www.usedby.ai/api/search?q=harvey"

{
  "tools": [
    {
      "id": "…",
      "name": "Harvey",
      "slug": "harvey",
      "logoUrl": "https://pub-938b8fa4d15e4a31aa3c88da5406a800.r2.dev/logos/tool/harvey.webp",
      "companyCount": 235,
      "category": "Legal AI"
    }
  ],
  "companies": [
    "… (trimmed)"
  ]
}

MCP server and JSON API

Connect Claude, Cursor or any MCP client to https://www.usedby.ai/mcp (Streamable HTTP). Read-only, no key. Each tool has a JSON twin under /api/v1 with the same answer: every line carries its proof level and its source.

With Claude Code: claude mcp add --transport http usedby https://www.usedby.ai/mcp

search_tools: Find a tool by name or category, with its number of public customers
GET /api/v1/tools?q=
who_uses: The companies that use a tool, with the proof level and source of each line
GET /api/v1/tools/<slug>/customers
company_stack: The AI tools a company uses
GET /api/v1/companies/<slug>/stack
recent_changes: Customers newly listed by the vendors
GET /api/v1/changes?days=
compare: Two tools side by side, with the companies that use both
GET /api/v1/compare?a=&b=

GET /api/v1 lists the endpoints. The OpenAPI description is at /api/v1/openapi.json and the server card at /.well-known/mcp.json.

Markdown versions of the pages

Add .md to the English URL of a page. The text follows the same rules as the page: every line shows its proof level, job-post signals included, and hidden lines stay hidden.

GET/tools/<slug>.mdWho uses a tool, with the proof level and source of each line

GET/companies/<slug>.mdThe AI tools a company uses

GET/companies/industry/<slug>.mdThe tools used by the companies of an industry

GET/tools/category/<slug>.mdThe tools of a category, ranked by public customers

GET/compare/<tool-a>-vs-<tool-b>.mdTwo tools side by side

GET/alternatives/<slug>.mdAlternatives to a tool in its category

GET/case-studies/<slug>.mdA customer story and what usedby checked

GET/methodology.mdHow usedby builds and checks each line

GET/changes.mdNewly listed customers

GET/llms.txtThe main sections and the Markdown versions, for AI assistants

English only. A French or Spanish page has the same data in its English Markdown version.

Site search: /api/search

GET /api/search?q=text returns up to 10 tools and 10 companies that contain the text: tools by name, tagline or description, companies by name or tagline.

tools[].companyCount: Public lines of the tool. Job-post signals are included in the count, as on the site.
companies[].toolCount: Public lines of the company, counted as on its company page. Job-post signals are included.
category, industry: Names in English.
slug: The page address: /tools/slug or /companies/slug, with .md for Markdown.

It has no version, so its shape can change. If you depend on it, tell us.

Call it from a server or a script. Browsers on other sites cannot call it.

Usage terms

No key and no contract. A few rules keep the data useful for everyone.

Link back: When you quote a number or a line, link to the usedby page it comes from: the HTML page, not the .md version.
Keep a polite pace: Stay under about 30 requests a minute and 300 an hour per IP, across the .md versions, /llms.txt and /api/search together. Above that they answer 429. A script that reads the other pages too fast is blocked for 1 minute. The MCP server and /api/v1 have their own budget: 30 requests a minute and 300 an hour per client, and at most 120 a minute and 1,200 an hour per IP. Above that they answer 429 with a Retry-After header. A 403 “Access denied” page means that your network is blocked: write to contact@usedby.ai.
Send corrections: See a wrong line? Write to contact@usedby.ai with the page and the line. How we check each line.
Bulk reuse: Quoting with a link is free. Reading usedby automatically within the rate limits is allowed. Collecting the data in bulk or above the limits, or copying the database, needs our written consent: see the terms of use.

What is coming

A keyed API is not available yet. Tell us what you need: contact@usedby.ai.

Tell us what you need